A Method for Detecting Motion Intent Based on Dynamic Stopping Strategy Combined with Ensemble Learning

A technology of motion detection and integrated learning, which is applied in the field of motion intention detection based on dynamic stopping strategy combined with integrated learning, can solve the problem of high computational cost of integrated learning algorithms, achieve considerable social and economic benefits, ensure accuracy and computing time, and make up for Computationally expensive effects

CN108764008BActive Publication Date: 2021-10-26TIANJIN UNIV
3 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Publication Date
2021-10-26

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a method for detecting motion intentions based on a dynamic stopping strategy combined with integrated learning, which includes the following steps: Offline modeling stage: after extracting features from the resting state data and the first pre-motion data, a linear discriminant analysis model is established, using To identify whether the current user is about to exercise; after extracting features from the second pre-motion data, construct a sub-classifier with the motion data features to detect the exact moment of motion; online testing phase: after extracting features from real-time intercepted data, Send it to the LDA model and output the decision value. If the decision value is greater than the set threshold, it will be sent to the constructed sub-classifier. Using the voting strategy, if the votes are greater than the set threshold, the result will be output. Otherwise, wait for the next data feature input. The invention realizes the online motion intention detection, and can obtain better detection results on the basis of the calculation cost of the control system.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the field of motion intention detection, in particular to a method for detecting motion intention based on dynamic stopping strategy combined with integrated learning. Background technique

[0002] Brain-Computer Interface (BCI) is a communication control system that does not depend on the normal output channels of peripheral nerves and muscles in the brain. Motor intention is the command and decision to control the peripheral nerves and skeletal muscles to complete the expected action by mobilizing the brain and motor-related cognitive resources when people are preparing to perform or imagine sports. In layman's terms, exercise intention is the mental preparation of the brain about exercise before the start of the exercise, or the initial thinking state of the central nervous system planning to participate in the exercise. Studies have shown that motor intentions can be detected by analyzing relevant features of EEG signals. ...

Examples

Embodiment 1

[0033] The embodiment of the present invention provides a method for detecting motion intention based on dynamic stopping strategy combined with integrated learning, see figure 1 , figure 2 , see the description below:

[0034] When people have motor intention output, a specific signal pattern present in EEG is generated before and after exercise, namely, motor-related cortical potentials (MRCPs). Because it is rich in a large amount of motion information and has strict time-locking and phase-locking characteristics, it has attracted extensive attention from researchers. The embodiment of the present invention designs a dynamic stopping strategy based on linear discriminant analysis combined with an integrated learning method, which can improve the accuracy of motion intention detection.

[0035] 101: Build an online experiment platform, read the user's EEG data in real time, preprocess the collected data, and extract features;

[0036] 102: Use the dynamic stop strategy b...

Embodiment 2

[0039] Combine below Figure 2-Figure 4 1. The specific example further introduces the scheme in embodiment 1, see the following description for details:

[0040] figure 2 It is a schematic diagram of the system design of the embodiment of the present invention. The design mainly includes: EEG signal acquisition, computer signal processing.

[0041] Use the electrode cap and EEG amplifier produced by Neuroscan to collect EEG. With the top of the head as the reference and the frontal lobe as the ground, 18 channel EEG signals (Fc5, Fc3, Fc1, Fc2, Fc5, Fc3, Fc1, Fc2, Fc4, Fc6, C5, C3, C1, C2, C4, C6, Cp5, Cp3, Cp1, Cp2, Cp4, Cp6, placed according to the 10-20 international standard lead position), sampling frequency 1000Hz, using 50Hz notch filter Eliminate power frequency interference. Computer signal processing uses MATLAB software to implement various signal processing algorithms.